metrics.py

# Adapted from https://github.com/meetshah1995/pytorch-semseg/blob/master/ptsemseg/metrics.py

import numpy as np
import torch


class runningScore(object):
    def __init__(self, n_classes):
        self.n_classes = n_classes
        self.confusion_matrix = np.zeros((n_classes, n_classes))

    def _fast_hist(self, label_true, label_pred, n_class):
        mask = (label_true >= 0) & (label_true < n_class)
        hist = np.bincount(
            n_class * label_true[mask].astype(int) + label_pred[mask], minlength=n_class ** 2
        ).reshape(n_class, n_class)
        return hist

    def update(self, label_trues, label_preds):
        if torch.is_tensor(label_trues):
            label_trues = label_trues.detach()
        if torch.is_tensor(label_preds):
            label_preds = label_preds.detach()
        for lt, lp in zip(label_trues, label_preds):
            self.confusion_matrix += self._fast_hist(lt.flatten(), lp.flatten(), self.n_classes)

    def get_scores(self):
        """Returns accuracy score evaluation result.
            - overall accuracy
            - mean accuracy
            - mean IU
            - fwavacc
        """
        hist = self.confusion_matrix
        acc = np.diag(hist).sum() / hist.sum()
        acc_cls = np.diag(hist) / hist.sum(axis=1)
        acc_cls = np.nanmean(acc_cls)
        iu = np.diag(hist) / (hist.sum(axis=1) + hist.sum(axis=0) - np.diag(hist))
        mean_iu = np.nanmean(iu)
        freq = hist.sum(axis=1) / hist.sum()
        fwavacc = (freq[freq > 0] * iu[freq > 0]).sum()
        cls_iu = dict(zip(range(self.n_classes), iu))

        return (
            {
                "Overall Acc: \t": acc,
                "Mean Acc : \t": acc_cls,
                "FreqW Acc : \t": fwavacc,
                "Mean IoU : \t": mean_iu,
            },
            cls_iu,
        )

    def reset(self):
        self.confusion_matrix = np.zeros((self.n_classes, self.n_classes))


class AverageMeter(object):
    """Computes and stores the average and current value"""

    def __init__(self):
        self.reset()

    def reset(self):
        self.val = 0
        self.avg = 0
        self.sum = 0
        self.count = 0

    def update(self, val, n=1):
        if torch.is_tensor(val):
            val = val.detach()
        self.val = val
        self.sum += val * n
        self.count += n
        self.avg = torch.true_divide(self.sum, self.count)


class AverageMeterDict(object):
    """Computes and stores the average and current value"""

    def __init__(self):
        self.reset()

    def reset(self):
        self.avgs = {}
        self.sums = {}
        self.counts = {}

    def update(self, vals, n=1):
        for k, v in vals.items():
            if torch.is_tensor(v):
                v = v.detach()
            if k not in self.sums:
                self.sums[k] = 0
                self.counts[k] = 0
            self.sums[k] += v * n
            self.counts[k] += n
            self.avgs[k] = torch.true_divide(self.sums[k], self.counts[k])